Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 317
    Prev
    Next
    INDEX
    Explanations

    preceding article "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    m
    0.30
    ం
    0.29
     collier
    0.29
    ך
    0.29
     vattum
    0.29
    okkal
    0.28
     thisStudent
    0.28
    ákat
    0.28
    ográf
    0.28
    ৬৫
    0.28
    POSITIVE LOGITS
    ال
    0.47
    е
    0.43
     be
    0.38
    لی
    0.37
     by
    0.36
     was
    0.35
    سی
    0.35
     avec
    0.34
     أ
    0.33
     în
    0.32
    Activations Density 0.557%

    No Known Activations